Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    legal terminology related to discrimination claims and the evaluation of evidence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.08
     betweenstory
    -0.84
     Мексичка
    -0.83
    السكان
    -0.74
    يكب
    -0.72
    iecie
    -0.71
    ніципалі
    -0.69
    Попис
    -0.69
    NUMX
    -0.69
    parsedMessage
    -0.68
    POSITIVE LOGITS
     Good
    0.51
     “
    0.46
     Do
    0.45
    Good
    0.43
     Re
    0.43
    ഘ
    0.41
     (
    0.41
     "
    0.41
     
    0.41
    Mis
    0.40
    Act Density 0.004%

    No Known Activations